Bioproject: PRJNA579391
EmptyDroplets (FDR <= 0.1) +
scDblFindersetwd("/media/jacopo/Elements/re_align/healthy/PRJNA579391/SAMN13110907/SRR10343068/")
# Load the libraries (from Sarah script + biomart)
library(tidyverse) # packages for data wrangling, visualization etc
library(Seurat) # scRNA-Seq analysis package
library(clustree) # plot of clustering tree
library(ggsignif) # Enrich your 'ggplots' with group-wise comparisons
library(clusterProfiler) #The package implements methods to analyze and visualize functional profiles of gene and gene clusters.
library(org.Hs.eg.db) # Human annotation package neede for clusterProfiler
library(ggrepel) # extra geoms for ggplo2
library(patchwork) #multiplots
library(reticulate)
Load and do the QC for the cellranger data
dat <- Read10X(data.dir ="./out/counts_filtered/")
dat <- CreateSeuratObject(dat) # Create the seurat object from the 10x data
kb.initial <- dat@assays[["RNA"]]@counts@Dim[[2]]
cat("Initial number of cells:", kb.initial,
"\nNumber of genes:", dat@assays[["RNA"]]@counts@Dim[[1]])
## Initial number of cells: 8368
## Number of genes: 36601
Empty cells were already filtered, check for % mt RNA and death markers:
# first calculate the mitochondrial percentage for each cell
dat$percent_mt <- PercentageFeatureSet(dat, pattern="^MT.")
# make violin plots
mt_rna = 20
max_counts = 20000
# Check some feature-feature relationships
# % mt RNA vs n Counts, n Features vs n Counts
VlnPlot(dat, features = c("nCount_RNA", "nFeature_RNA", "percent_mt")) + geom_hline(yintercept=mt_rna, linetype = "dotted")
plot1 <- FeatureScatter(dat, feature1 = "nCount_RNA", feature2 = "percent_mt")
plot1 <- plot1 + geom_hline(yintercept=mt_rna, linetype = "dotted")
plot2 <- FeatureScatter(dat, feature1 = "nCount_RNA", feature2 = "nFeature_RNA")
plot2 <- plot2 + geom_vline(xintercept = max_counts, linetype = "dotted")
plot1
plot2
## cells retained by mt RNA content ( 20 %): 6779
## percentage of retained cells: 81.01 %
## cells retained by counts ( 20000 ): 6766
## percentage of retained cells: 80.86 %
Check the distribution of the cells with low counts and control death markers:
min_counts = 200
hist(dat@meta.data$nCount_RNA, breaks = 100, xlab = "Counts")
hist(dat@meta.data$nCount_RNA, breaks = 500, xlab = "Counts", xlim = c(0,5000))
hist(dat@meta.data$nCount_RNA, breaks = 10000, xlab = "Counts", xlim = c(0,1000))
abline(v=min_counts, col="red", lty = 3)
# Subset the dataset to focus only on those cells with low counts
dat.lowcount <- subset(dat, subset = nCount_RNA < min_counts)
# Get the mean of the counts for each gene and sort them decreasing
meanCounts <- rowMeans(GetAssayData(object = dat.lowcount, slot = 'counts'))
meanCounts <- sort(meanCounts, decreasing = T)
# A boxplot can help to observe the distribution of the means
#boxplot(meanCounts)
# Print the most highly expressed genes
head(meanCounts, 20)
## MALAT1 RPLP1 RPS12 RPS6 RPS18 RPS3A RPL13A RPS4X
## 2.3870968 1.3479263 1.1981567 1.1866359 1.1658986 1.1152074 1.0622120 1.0322581
## RPL26 RPS23 RPL13 RPL41 RPL7 EEF1A1 RPL21 PTMA
## 0.9838710 0.9827189 0.9792627 0.9781106 0.9654378 0.9377880 0.9262673 0.9124424
## RPL34 RPS24 RPL17 RPS2
## 0.9043779 0.8479263 0.8444700 0.8341014
## cells retained by counts ( 200 ): 5897
## percentage of retained cells: 70.47 %
dir.create("result")
saveRDS(dat, file = "./result/SRR10343068_clean_QC.RDS")
#Normalize
dat <- NormalizeData(dat)
# Find the first 4000 variabe features
dat <- FindVariableFeatures(dat, selection.method = "vst", nfeatures = 4000)
Set mean expression to 0 and variance across 1 to avoid highly expressed genes drive the forwarding analyses. Since negative expression is meaningless, scaled data are useful only for UMAP and clustering
# scale data, the scaled data are saved in:
# dat[["RNA"]]@scale.data
all.genes <- rownames(dat)
dat <- ScaleData(dat, vars.to.regress = c("percent_mt","nCount_RNA"))
dat <- RunPCA(dat, features = VariableFeatures(object = dat), verbose = F, seed.use = 1)
print(dat[["pca"]], dims = 1:5, nfeatures = 5)
## PC_ 1
## Positive: CYTL1, CNRIP1, HBD, KLF1, APOC1
## Negative: TMSB4X, LGALS1, CYBA, VIM, CORO1A
## PC_ 2
## Positive: HBB, APOC1, CA1, HBD, AHSP
## Negative: SPINK2, AIF1, C1QTNF4, HOPX, MGST1
## PC_ 3
## Positive: IGLL1, DNTT, VPREB1, CD79B, VPREB3
## Negative: S100A6, S100A4, LYZ, CST3, LGALS1
## PC_ 4
## Positive: MPO, PRTN3, AZU1, ELANE, MIF
## Negative: JCHAIN, IRF7, CCDC50, CD74, UGCG
## PC_ 5
## Positive: DNTT, VPREB1, CD79B, VPREB3, IGLL1
## Negative: CD164, FCER1A, GP1BB, AL157895.1, PBX1
UMAP is a graph-based method of clustering. The first step in this process is to construct a KNN graph based on the euclidean distance in PCA space:
dat <- FindNeighbors(dat, dims = 1:20)
The graph now can be used as input for the function
runUMAP()
dat <- RunUMAP(dat, dims = 1:20, seed.use = 1)
DimPlot(dat, reduction = 'umap', seed = 1)
## QC metrics
## markers